net/rds: Use DMA memory pool allocation for rds_header

Currently, RDS calls ib_dma_alloc_coherent() to allocate a large piece
of contiguous DMA coherent memory to store struct rds_header for
sending/receiving packets.  The memory allocated is then partitioned
into struct rds_header.  This is not necessary and can be costly at
times when memory is fragmented.  Instead, RDS should use the DMA
memory pool interface to handle this.  The DMA addresses of the pre-
allocated headers are stored in an array.  At send/receive ring
initialization and refill time, this arrary is de-referenced to get
the DMA addresses.  This array is not accessed at send/receive packet
processing.

Suggested-by: Håkon Bugge <haakon.bugge@oracle.com>
Signed-off-by: Ka-Cheong Poon <ka-cheong.poon@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 121 insertions, 45 deletions

diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c
index 233f1368162b..d08251f4a00c 100644
--- a/net/rds/ib_cm.c
+++ b/net/rds/ib_cm.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006, 2018 Oracle and/or its affiliates. All rights reserved.
+ * Copyright (c) 2006, 2019 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -439,6 +439,68 @@ static inline void ibdev_put_vector(struct rds_ib_device *rds_ibdev, int index)
 	rds_ibdev->vector_load[index]--;
 }
 
+/* Allocate DMA coherent memory to be used to store struct rds_header for
+ * sending/receiving packets.  The pointers to the DMA memory and the
+ * associated DMA addresses are stored in two arrays.
+ *
+ * @ibdev: the IB device
+ * @pool: the DMA memory pool
+ * @dma_addrs: pointer to the array for storing DMA addresses
+ * @num_hdrs: number of headers to allocate
+ *
+ * It returns the pointer to the array storing the DMA memory pointers.  On
+ * error, NULL pointer is returned.
+ */
+struct rds_header **rds_dma_hdrs_alloc(struct ib_device *ibdev,
+				       struct dma_pool *pool,
+				       dma_addr_t **dma_addrs, u32 num_hdrs)
+{
+	struct rds_header **hdrs;
+	dma_addr_t *hdr_daddrs;
+	u32 i;
+
+	hdrs = kvmalloc_node(sizeof(*hdrs) * num_hdrs, GFP_KERNEL,
+			     ibdev_to_node(ibdev));
+	if (!hdrs)
+		return NULL;
+
+	hdr_daddrs = kvmalloc_node(sizeof(*hdr_daddrs) * num_hdrs, GFP_KERNEL,
+				   ibdev_to_node(ibdev));
+	if (!hdr_daddrs) {
+		kvfree(hdrs);
+		return NULL;
+	}
+
+	for (i = 0; i < num_hdrs; i++) {
+		hdrs[i] = dma_pool_zalloc(pool, GFP_KERNEL, &hdr_daddrs[i]);
+		if (!hdrs[i]) {
+			rds_dma_hdrs_free(pool, hdrs, hdr_daddrs, i);
+			return NULL;
+		}
+	}
+
+	*dma_addrs = hdr_daddrs;
+	return hdrs;
+}
+
+/* Free the DMA memory used to store struct rds_header.
+ *
+ * @pool: the DMA memory pool
+ * @hdrs: pointer to the array storing DMA memory pointers
+ * @dma_addrs: pointer to the array storing DMA addresses
+ * @num_hdars: number of headers to free.
+ */
+void rds_dma_hdrs_free(struct dma_pool *pool, struct rds_header **hdrs,
+		       dma_addr_t *dma_addrs, u32 num_hdrs)
+{
+	u32 i;
+
+	for (i = 0; i < num_hdrs; i++)
+		dma_pool_free(pool, hdrs[i], dma_addrs[i]);
+	kvfree(hdrs);
+	kvfree(dma_addrs);
+}
+
 /*
  * This needs to be very careful to not leave IS_ERR pointers around for
  * cleanup to trip over.
@@ -451,6 +513,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
 	struct ib_cq_init_attr cq_attr = {};
 	struct rds_ib_device *rds_ibdev;
 	int ret, fr_queue_space;
+	struct dma_pool *pool;
 
 	/*
 	 * It's normal to see a null device if an incoming connection races
@@ -541,31 +604,28 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
 		goto recv_cq_out;
 	}
 
-	ic->i_send_hdrs = ib_dma_alloc_coherent(dev,
-					   ic->i_send_ring.w_nr *
-						sizeof(struct rds_header),
-					   &ic->i_send_hdrs_dma, GFP_KERNEL);
+	pool = rds_ibdev->rid_hdrs_pool;
+	ic->i_send_hdrs = rds_dma_hdrs_alloc(dev, pool, &ic->i_send_hdrs_dma,
+					     ic->i_send_ring.w_nr);
 	if (!ic->i_send_hdrs) {
 		ret = -ENOMEM;
-		rdsdebug("ib_dma_alloc_coherent send failed\n");
+		rdsdebug("DMA send hdrs alloc failed\n");
 		goto qp_out;
 	}
 
-	ic->i_recv_hdrs = ib_dma_alloc_coherent(dev,
-					   ic->i_recv_ring.w_nr *
-						sizeof(struct rds_header),
-					   &ic->i_recv_hdrs_dma, GFP_KERNEL);
+	ic->i_recv_hdrs = rds_dma_hdrs_alloc(dev, pool, &ic->i_recv_hdrs_dma,
+					     ic->i_recv_ring.w_nr);
 	if (!ic->i_recv_hdrs) {
 		ret = -ENOMEM;
-		rdsdebug("ib_dma_alloc_coherent recv failed\n");
+		rdsdebug("DMA recv hdrs alloc failed\n");
 		goto send_hdrs_dma_out;
 	}
 
-	ic->i_ack = ib_dma_alloc_coherent(dev, sizeof(struct rds_header),
-				       &ic->i_ack_dma, GFP_KERNEL);
+	ic->i_ack = dma_pool_zalloc(pool, GFP_KERNEL,
+				    &ic->i_ack_dma);
 	if (!ic->i_ack) {
 		ret = -ENOMEM;
-		rdsdebug("ib_dma_alloc_coherent ack failed\n");
+		rdsdebug("DMA ack header alloc failed\n");
 		goto recv_hdrs_dma_out;
 	}
 
@@ -596,17 +656,23 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
 
 sends_out:
 	vfree(ic->i_sends);
+
 ack_dma_out:
-	ib_dma_free_coherent(dev, sizeof(struct rds_header),
-			     ic->i_ack, ic->i_ack_dma);
+	dma_pool_free(pool, ic->i_ack, ic->i_ack_dma);
+	ic->i_ack = NULL;
+
 recv_hdrs_dma_out:
-	ib_dma_free_coherent(dev, ic->i_recv_ring.w_nr *
-					sizeof(struct rds_header),
-					ic->i_recv_hdrs, ic->i_recv_hdrs_dma);
+	rds_dma_hdrs_free(pool, ic->i_recv_hdrs, ic->i_recv_hdrs_dma,
+			  ic->i_recv_ring.w_nr);
+	ic->i_recv_hdrs = NULL;
+	ic->i_recv_hdrs_dma = NULL;
+
 send_hdrs_dma_out:
-	ib_dma_free_coherent(dev, ic->i_send_ring.w_nr *
-					sizeof(struct rds_header),
-					ic->i_send_hdrs, ic->i_send_hdrs_dma);
+	rds_dma_hdrs_free(pool, ic->i_send_hdrs, ic->i_send_hdrs_dma,
+			  ic->i_send_ring.w_nr);
+	ic->i_send_hdrs = NULL;
+	ic->i_send_hdrs_dma = NULL;
+
 qp_out:
 	rdma_destroy_qp(ic->i_cm_id);
 recv_cq_out:
@@ -984,8 +1050,6 @@ void rds_ib_conn_path_shutdown(struct rds_conn_path *cp)
 		 ic->i_cm_id ? ic->i_cm_id->qp : NULL);
 
 	if (ic->i_cm_id) {
-		struct ib_device *dev = ic->i_cm_id->device;
-
 		rdsdebug("disconnecting cm %p\n", ic->i_cm_id);
 		err = rdma_disconnect(ic->i_cm_id);
 		if (err) {
@@ -1035,24 +1099,39 @@ void rds_ib_conn_path_shutdown(struct rds_conn_path *cp)
 			ib_destroy_cq(ic->i_recv_cq);
 		}
 
-		/* then free the resources that ib callbacks use */
-		if (ic->i_send_hdrs)
-			ib_dma_free_coherent(dev,
-					   ic->i_send_ring.w_nr *
-						sizeof(struct rds_header),
-					   ic->i_send_hdrs,
-					   ic->i_send_hdrs_dma);
-
-		if (ic->i_recv_hdrs)
-			ib_dma_free_coherent(dev,
-					   ic->i_recv_ring.w_nr *
-						sizeof(struct rds_header),
-					   ic->i_recv_hdrs,
-					   ic->i_recv_hdrs_dma);
-
-		if (ic->i_ack)
-			ib_dma_free_coherent(dev, sizeof(struct rds_header),
-					     ic->i_ack, ic->i_ack_dma);
+		if (ic->rds_ibdev) {
+			struct dma_pool *pool;
+
+			pool = ic->rds_ibdev->rid_hdrs_pool;
+
+			/* then free the resources that ib callbacks use */
+			if (ic->i_send_hdrs) {
+				rds_dma_hdrs_free(pool, ic->i_send_hdrs,
+						  ic->i_send_hdrs_dma,
+						  ic->i_send_ring.w_nr);
+				ic->i_send_hdrs = NULL;
+				ic->i_send_hdrs_dma = NULL;
+			}
+
+			if (ic->i_recv_hdrs) {
+				rds_dma_hdrs_free(pool, ic->i_recv_hdrs,
+						  ic->i_recv_hdrs_dma,
+						  ic->i_recv_ring.w_nr);
+				ic->i_recv_hdrs = NULL;
+				ic->i_recv_hdrs_dma = NULL;
+			}
+
+			if (ic->i_ack) {
+				dma_pool_free(pool, ic->i_ack, ic->i_ack_dma);
+				ic->i_ack = NULL;
+			}
+		} else {
+			WARN_ON(ic->i_send_hdrs);
+			WARN_ON(ic->i_send_hdrs_dma);
+			WARN_ON(ic->i_recv_hdrs);
+			WARN_ON(ic->i_recv_hdrs_dma);
+			WARN_ON(ic->i_ack);
+		}
 
 		if (ic->i_sends)
 			rds_ib_send_clear_ring(ic);
@@ -1071,9 +1150,6 @@ void rds_ib_conn_path_shutdown(struct rds_conn_path *cp)
 		ic->i_pd = NULL;
 		ic->i_send_cq = NULL;
 		ic->i_recv_cq = NULL;
-		ic->i_send_hdrs = NULL;
-		ic->i_recv_hdrs = NULL;
-		ic->i_ack = NULL;
 	}
 	BUG_ON(ic->rds_ibdev);